New dnn engine #26056
This is the 1st PR with the new engine; CI is green and PR is ready to be merged, I think.
Merge together with https://github.com/opencv/opencv_contrib/pull/3794
---
**Known limitations:**
* [solved] OpenVINO is temporarily disabled, but is probably easy to restore (it's not a deal breaker to merge this PR, I guess)
* The new engine does not support any backends nor any targets except for the default CPU implementation. But it's possible to choose the old engine when loading a model, then all the functionality is available.
* [Caffe patch is here: #26208] The new engine only supports ONNX. When a model is constructed manually or is loaded from a file of different format (.tf, .tflite, .caffe, .darknet), the old engine is used.
* Even in the case of ONNX some layers are not supported by the new engine, such as all quantized layers (including DequantizeLinear, QuantizeLinear, QLinearConv etc.), LSTM, GRU, .... It's planned, of course, to have full support for ONNX by OpenCV 5.0 gold release. When a loaded model contains unsupported layers, we switch to the old engine automatically (at ONNX parsing time, not at `forward()` time).
* Some layers , e.g. Expat, are only partially supported by the new engine. In the case of unsupported flavours it switches to the old engine automatically (at ONNX parsing time, not at `forward()` time).
* 'Concat' graph optimization is disabled. The optimization eliminates Concat layer and instead makes the layers that generate tensors to be concatenated to write the outputs to the final destination. Of course, it's only possible when `axis=0` or `axis=N=1`. The optimization is not compatible with dynamic shapes since we need to know in advance where to store the tensors. Because some of the layer implementations have been modified to become more compatible with the new engine, the feature appears to be broken even when the old engine is used.
* Some `dnn::Net` API is not available with the new engine. Also, shape inference may return false if some of the output or intermediate tensors' shapes cannot be inferred without running the model. Probably this can be fixed by a dummy run of the model with zero inputs.
* Some overloads of `dnn::Net::getFLOPs()` and `dnn::Net::getMemoryConsumption()` are not exposed any longer in wrapper generators; but the most useful overloads are exposed (and checked by Java tests).
* [in progress] A few Einsum tests related to empty shapes have been disabled due to crashes in the tests and in Einsum implementations. The code and the tests need to be repaired.
* OpenCL implementation of Deconvolution is disabled. It's very bad and very slow anyway; need to be completely revised.
* Deconvolution3D test is now skipped, because it was only supported by CUDA and OpenVINO backends, both of which are not supported by the new engine.
* Some tests, such as FastNeuralStyle, checked that the in the case of CUDA backend there is no fallback to CPU. Currently all layers in the new engine are processed on CPU, so there are many fallbacks. The checks, therefore, have been temporarily disabled.
---
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
dnn: add ONNX TopK #23279
Merge with https://github.com/opencv/opencv_extra/pull/1200
Partially fixes#22890 and #20258
To-do:
- [x] TopK forward impl
- [x] add tests
- [x] support Opset 1 & 10 if possible
- [ ] ~Support other backends~ (TopK has two outputs, which is not supported by other backends, such as openvino)
Perf:
M1 (time in millisecond)
| input shape | axis | dnn | ort |
| --------------- | ---- | ---- | ---- |
| (1000, 100) | 0 | 1.68 | 4.07 |
| (1000, 100) K5 | 0 | 1.13 | 0.12 |
| (1000, 100) | 1 | 0.96 | 0.77 |
| (100, 100, 100) | 0 | 10.00 | 31.13 |
| (100, 100, 100) | 1 | 7.33 | 9.17 |
| (100, 100, 100) | 2 | 7.52 | 9.48 |
M2 (time in milisecond)
| input shape | axis | dnn | ort |
| --------------- | ---- | ---- | ---- |
| (1000, 100) | 0 | 0.76 | 2.44 |
| (1000, 100) K5 | 0 | 0.68 | 0.07 |
| (1000, 100) | 1 | 0.41 | 0.50 |
| (100, 100, 100) | 0 | 4.83 | 17.52|
| (100, 100, 100) | 1 | 3.60 | 5.08 |
| (100, 100, 100) | 2 | 3.73 | 5.10 |
ONNXRuntime performance testing script: https://gist.github.com/fengyuentau/a119f94fd16721ec9974b8c7b0a45d4c
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
dnn: optimize activations with v_exp #25881
Merge with https://github.com/opencv/opencv_extra/pull/1191.
This PR optimizes the following activations:
- [x] Swish
- [x] Mish
- [x] Elu
- [x] Celu
- [x] Selu
- [x] HardSwish
### Performance (Updated on 2024-07-18)
#### AmLogic A311D2 (ARM Cortex A73 + A53)
```
Geometric mean (ms)
Name of Test activations activations.patch activations.patch
vs
activations
(x-factor)
Celu::Layer_Elementwise::OCV/CPU 115.859 27.930 4.15
Elu::Layer_Elementwise::OCV/CPU 27.846 27.003 1.03
Gelu::Layer_Elementwise::OCV/CPU 0.657 0.602 1.09
HardSwish::Layer_Elementwise::OCV/CPU 31.885 6.781 4.70
Mish::Layer_Elementwise::OCV/CPU 35.729 32.089 1.11
Selu::Layer_Elementwise::OCV/CPU 61.955 27.850 2.22
Swish::Layer_Elementwise::OCV/CPU 30.819 26.688 1.15
```
#### Apple M1
```
Geometric mean (ms)
Name of Test activations activations.patch activations.patch
vs
activations
(x-factor)
Celu::Layer_Elementwise::OCV/CPU 16.184 2.118 7.64
Celu::Layer_Elementwise::OCV/CPU_FP16 16.280 2.123 7.67
Elu::Layer_Elementwise::OCV/CPU 9.123 1.878 4.86
Elu::Layer_Elementwise::OCV/CPU_FP16 9.085 1.897 4.79
Gelu::Layer_Elementwise::OCV/CPU 0.089 0.081 1.11
Gelu::Layer_Elementwise::OCV/CPU_FP16 0.086 0.074 1.17
HardSwish::Layer_Elementwise::OCV/CPU 1.560 1.555 1.00
HardSwish::Layer_Elementwise::OCV/CPU_FP16 1.536 1.523 1.01
Mish::Layer_Elementwise::OCV/CPU 6.077 2.476 2.45
Mish::Layer_Elementwise::OCV/CPU_FP16 5.990 2.496 2.40
Selu::Layer_Elementwise::OCV/CPU 11.351 1.976 5.74
Selu::Layer_Elementwise::OCV/CPU_FP16 11.533 1.985 5.81
Swish::Layer_Elementwise::OCV/CPU 4.687 1.890 2.48
Swish::Layer_Elementwise::OCV/CPU_FP16 4.715 1.873 2.52
```
#### Intel i7-12700K
```
Geometric mean (ms)
Name of Test activations activations.patch activations.patch
vs
activations
(x-factor)
Celu::Layer_Elementwise::OCV/CPU 17.106 3.560 4.81
Elu::Layer_Elementwise::OCV/CPU 5.064 3.478 1.46
Gelu::Layer_Elementwise::OCV/CPU 0.036 0.035 1.04
HardSwish::Layer_Elementwise::OCV/CPU 2.914 2.893 1.01
Mish::Layer_Elementwise::OCV/CPU 3.820 3.529 1.08
Selu::Layer_Elementwise::OCV/CPU 10.799 3.593 3.01
Swish::Layer_Elementwise::OCV/CPU 3.651 3.473 1.05
```
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
* added v_erf and implemented gelu acceleration via vectorization
* remove anonymous v_erf and use v_erf from intrin_math
* enable perf for ov and cuda backend
Change opencv_face_detector related tests and samples from caffe to onnx #25463
Part of https://github.com/opencv/opencv/issues/25314
This PR aims to change the tests related to opencv_face_detector from caffe framework to onnx. Tests in `test_int8_layer.cpp` and `test_caffe_importer.cpp` will be removed in https://github.com/opencv/opencv/pull/25323
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
Added int32, int64 support and type inference to dnn #24411
**Added a type inference to dnn similar to the shape inference, added int32 and int64 support.**
- Added getTypes method for layers that calculates layer outputs types and internals types from inputs types (Similar to getMemoryShapes). By default outputs and internals types = input[0] type
- Added type inference pipeline similar to shape inference pipeline. LayersShapes struct (that is used in shape inference pipeline) now contains both shapes and types
- All layers output blobs are now allocated using the calculated types from the type inference.
- Inputs and constants with int32 and int64 types are not automatically converted into float32 now.
- Added int32 and int64 support for all the layers with indexing and for all the layers required in tests.
Added int32 and int64 support for CUDA:
- Added host<->device data moving for int32 and int64
- Added int32 and int64 support for several layers (just slightly modified CUDA C++ templates)
Passed all the accuracy tests on CPU, OCL, OCL_FP16, CUDA, CUDA_FP16. (except RAFT model)
**CURRENT PROBLEMS**:
- ONNX parser always converts int64 constants and layers attributes to int32, so some models with int64 constants doesn't work (e.g. RAFT). The solution is to disable int64->int32 conversion and fix attributes reading in a lot of ONNX layers parsers (https://github.com/opencv/opencv/issues/25102)
- I didn't add type inference and int support to VULCAN, so it doesn't work at all now.
- Some layers don't support int yet, so some unknown models may not work.
**CURRENT WORKAROUNDS**:
- CPU arg_layer indides are implemented in int32 followed by a int32->int64 conversion (the master branch has the same workaround with int32->float conversion)
- CPU and OCL pooling_layer indices are implemented in float followed by a float->int64 conversion
- CPU gather_layer indices are implemented in int32, so int64 indices are converted to int32 (the master branch has the same workaround with float->int32 conversion)
**DISABLED TESTS**:
- RAFT model
**REMOVED TESTS**:
- Greater_input_dtype_int64 (because it doesn't fit ONNX rules, the whole test is just comparing float tensor with int constant)
**TODO IN NEXT PULL REQUESTS**:
- Add int64 support for ONNX parser
- Add int support for more layers
- Add int support for OCL (currently int layers just run on CPU)
- Add int tests
- Add int support for other backends
Vulkan backend for NaryEltwiseLayer in DNN module #24768
We improve Vulkan backend for ``NaryEltwiseLayer`` in DNN module by:
- add a basic framework for Vulkan backend in ``NaryEltwiseLayer``
- add a compute shader for binary forwarding (an imitation of what has been done in native OpenCV backend including broadcasting and eltwise-operation)
- typo fixed:
- Wrong info output in ``context.cpp``
Currently, our implementation (or all layers supporting Vulkan backend) runs pretty slow on discrete GPUs basically due to IO cost in function ``copyToHost``, and we are going to fix that by
- find out the best ``VkMemoryProperty`` for various discrete GPUs
- prevent ``copyToHost`` in middle layers during forwarding, (i.e keep data in GPU memory)
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
Co-authored-by: IskXCr <IskXCr@outlook.com>
dnn onnx: add group norm layer #24610
dnn onnx: add group norm layer
Todo:
- [x] speed up by multi-threading
- [x] add perf
- [x] add backend: OpenVINO
- [x] add backend: CUDA
- [x] add backend: OpenCL (no fp16)
- [ ] add backend: CANN
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
Co-authored-by: fengyuentau <yuantao.feng@opencv.org.cn>
dnn: add attention layer #24476Resolves#24609
Merge with: https://github.com/opencv/opencv_extra/pull/1128.
Attention operator spec from onnxruntime: https://github.com/microsoft/onnxruntime/blob/v1.16.1/docs/ContribOperators.md#com.microsoft.Attention.
TODO:
- [x] benchmark (before this PR vs. with this PR vs. ORT).
- [x] Layer fusion: Take care Slice with end=INT64_MAX.
- [x] Layer fusion: match more potential attention (VIT) patterns.
- [x] Single-head attention is supported.
- [x] Test AttentionSubgraph fusion.
- [x] Add acc tests for VIT_B_32 and VitTrack
- [x] Add perf tests for VIT_B_32 and VitTrack
## Benchmarks
Platform: Macbook Air M1.
### Attention Subgraph
Input scale: [1, 197, 768].
| | mean (ms) | median (ms) | min (ms) |
| ---------------------- | --------- | ----------- | -------- |
| w/ Attention (this PR) | 3.75 | 3.68 | 3.22 |
| w/o Attention | 9.06 | 9.01 | 8.24 |
| ORT (python) | 4.32 | 2.63 | 2.50 |
### ViTs
All data in millisecond (ms).
| ViTs | With Attention | Without Attention | ORT |
| -------- | -------------- | ----------------- | ------ |
| vit_b_16 | 302.77 | 365.35 | 109.70 |
| vit_b_32 | 89.92 | 116.22 | 30.36 |
| vit_l_16 | 1593.32 | 1730.74 | 419.92 |
| vit_l_32 | 468.11 | 577.41 | 134.12 |
| VitTrack | 3.80 | 3.87 | 2.25 |
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
dnn: refactor ONNX MatMul with fastGemm #24694
Done:
- [x] add backends
- [x] CUDA
- [x] OpenVINO
- [x] CANN
- [x] OpenCL
- [x] Vulkan
- [x] add perf tests
- [x] const B case
### Benchmark
Tests are done on M1. All data is in milliseconds (ms).
| Configuration | MatMul (Prepacked) | MatMul | InnerProduct |
| - | - | - | - |
| A=[12, 197, 197], B=[12, 197, 64], trans_a=0, trans_b=0 | **0.39** | 0.41 | 1.33 |
| A=[12, 197, 64], B=[12, 64, 197], trans_a=0, trans_b=0 | **0.42** | 0.42 | 1.17 |
| A=[12, 50, 64], B=[12, 64, 50], trans_a=0, trans_b=0 | **0.13** | 0.15 | 0.33 |
| A=[12, 50, 50], B=[12, 50, 64], trans_a=0, trans_b=0 | **0.11** | 0.13 | 0.22 |
| A=[16, 197, 197], B=[16, 197, 64], trans_a=0, trans_b=0 | **0.46** | 0.54 | 1.46 |
| A=[16, 197, 64], B=[16, 64, 197], trans_a=0, trans_b=0 | **0.46** | 0.95 | 1.74 |
| A=[16, 50, 64], B=[16, 64, 50], trans_a=0, trans_b=0 | **0.18** | 0.32 | 0.43 |
| A=[16, 50, 50], B=[16, 50, 64], trans_a=0, trans_b=0 | **0.15** | 0.25 | 0.25 |
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
Classify and extend convolution and depthwise performance tests #24547
This PR aims to:
1. Extend the test cases from models: `YOLOv5`, `YOLOv8`, `EfficientNet`, `YOLOX`, `YuNet`, `SFace`, `MPPalm`, `MPHand`, `MPPose`, `ViTTrack`, `PPOCRv3`, `CRNN`, `PPHumanSeg`. (371 new test cases are added)
2. Classify the existing convolution performance test to below cases
- CONV_1x1
- CONV_3x3_S1_D1 (winograd)
- CONV
- DEPTHWISE
3. Reduce unnecessary test cases by follow 3 rules (366 test cases are pruned):
(i). For all tests, except for pad and bias related parameters, all other parameters are the same. Only one case can be reserved.
(ii). When the only difference is the channel of input shape, and other parameters are the same. Only one case can be reserved in each range `[1, 3], [4, 7], [8, 15], [16, 31], [32, 63], [64, 127], [128, 255], [256, 511], [512, 1023], [1024, 2047], [2048, 4095]`
(iii). When the only difference is the width and height of input shape, and other parameters are the same. Only one case can be reserved in each range `[1, 31], [32, 63], [64, 95]... `
> **Reproduced**: 1. follow step in https://github.com/alalek/opencv/commit/dnn_dump_conv_kernels to dump all convolution cases from new models. (declared flops may not right, need to be checked manually) 2 and 3. Use the script from python code [classify conv.txt](https://github.com/opencv/opencv/files/13522228/classify.conv.txt)
**Performance test result on Apple M2**
**Test result details**: [M2.md](https://github.com/opencv/opencv/files/13379189/M2.md)
**Additional test result details with FP16**: [m2_results_with_fp16.zip](https://github.com/opencv/opencv/files/13491070/m2_results_with_fp16.zip)
**Brief summary for 4.8.1 vs 4.7.0 or 4.6.0**:
1. `CONV_1x1_S1_D1` dropped significant with small or large input shape.
2. `DEPTHWISE_5x5 ` dropped a little compared with 4.7.0.
---
**Performance test result on [Intel Core i7-12700K](https://www.intel.com/content/www/us/en/products/sku/134594/intel-core-i712700k-processor-25m-cache-up-to-5-00-ghz/specifications.html)**: 8 Performance-cores (3.60 GHz, turbo up to 4.90 GHz), 4 Efficient-cores (2.70 GHz, turbo up to 3.80 GHz), 20 threads.
**Test result details**: [INTEL.md](https://github.com/opencv/opencv/files/13374093/INTEL.md)
**Brief summary for 4.8.1 vs 4.5.5**:
1. `CONV_5x5_S1_D1` dropped significant.
2. `CONV_1x1_S1_D1`, `CONV_3x3_S1_D1`, `DEPTHWISE_3x3_S1_D1`, `DEPTHWISW_3x3_S2_D1` dropped with small input shape.
---
TODO:
- [x] Perform tests on arm with each opencv version
- [x] Perform tests on x86 with each opencv version
- [x] Split each test classification with single test config
- [x] test enable fp16
Fast gemm for einsum #24509
## This PR adds performance tests for Einsum Layer with FastGemm. See below results of performance test on different inputs
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
dnn onnx: add instance norm layer #24378
Resolves https://github.com/opencv/opencv/issues/24377
Relates https://github.com/opencv/opencv/pull/24092#discussion_r1349841644
| Perf | multi-thread | single-thread |
| - | - | - |
| x: [2, 64, 180, 240] | 3.95ms | 11.12ms |
Todo:
- [x] speed up by multi-threading
- [x] add perf
- [x] add backend: OpenVINO
- [x] add backend: CUDA
- [x] add backend: OpenCL (no fp16)
- [ ] add backend: CANN (will be done via https://github.com/opencv/opencv/pull/24462)
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
```
force_builders=Linux OpenCL,Win64 OpenCL,Custom
buildworker:Custom=linux-4
build_image:Custom=ubuntu:18.04
modules_filter:Custom=none
disable_ipp:Custom=ON
```
* improve and refactor softmax layer
* fix building error
* compatible region layer
* fix axisStep when disable SIMD
* fix dynamic array
* try to fix error
* use nlanes from VTraits
* move axisBias to srcOffset
* fix bug caused by axisBias
* remove macro
* replace #ifdef with #if for CV_SIMD
Remove torch (old torch7) from dnn in 5.x #24294
Merge with https://github.com/opencv/opencv_extra/pull/1097
Completely removed torch (old torch7) from dnn:
- removed modules/dnn/src/torch directory that contained torch7 model parser
- removed readNetFromTorch() and readTorchBlob() public functions
- removed torch7 references from comments and help texts
- replaced links to t7 models by links to similar onnx models in js_style_transfer turtorial (similar to https://github.com/opencv/opencv/pull/24245/files)
GSoC Add ONNX Support for GatherElements #24092
Merge with: https://github.com/opencv/opencv_extra/pull/1082
Adds support to the ONNX operator GatherElements [operator docs](https://github.com/onnx/onnx/blob/main/docs/Operators.md#GatherElements)
Added tests to opencv_extra at pull request https://github.com/opencv/opencv_extra/pull/1082
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
dnn: cleanup of halide backend for 5.x #24231
Merge with https://github.com/opencv/opencv_extra/pull/1092.
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
OpenVINO backend for INT8 models #23987
### Pull Request Readiness Checklist
TODO:
- [x] DetectionOutput layer (https://github.com/opencv/opencv/pull/24069)
- [x] Less FP32 fallbacks (i.e. Sigmoid, eltwise sum)
- [x] Accuracy, performance tests (https://github.com/opencv/opencv/pull/24039)
- [x] Single layer tests (convolution)
- [x] ~~Fixes for OpenVINO 2022.1 (https://pullrequest.opencv.org/buildbot/builders/precommit_custom_linux/builds/100334)~~
Performace results for object detection model `coco_efficientdet_lite0_v1_1.0_quant_2021_09_06.tflite`:
| backend | performance (median time) |
|---|---|
| OpenCV | 77.42ms |
| OpenVINO 2023.0 | 10.90ms |
CPU: `11th Gen Intel(R) Core(TM) i5-1135G7 @ 2.40GHz`
Serialized model per-layer stats (note that Convolution should use `*_I8` primitives if they are quantized correctly): https://gist.github.com/dkurt/7772bbf1907035441bb5454f19f0feef
---
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
* first commit
* turned C from input to constant; force C constant in impl; better handling 0d/1d cases
* integrate with gemm from ficus nn
* fix const inputs
* adjust threshold for int8 tryQuantize
* adjust threshold for int8 quantized 2
* support batched gemm and matmul; tune threshold for rcnn_ilsvrc13; update googlenet
* add gemm perf against innerproduct
* add perf tests for innerproduct with bias
* fix perf
* add memset
* renamings for next step
* add dedicated perf gemm
* add innerproduct in perf_gemm
* remove gemm and innerproduct perf tests from perf_layer
* add perf cases for vit sizes; prepack constants
* remove batched gemm; fix wrong trans; optimize KC
* remove prepacking for const A; several fixes for const B prepacking
* add todos and gemm expression
* add optimized branch for avx/avx2
* trigger build
* update macros and signature
* update signature
* fix macro
* fix bugs for neon aarch64 & x64
* add backends: cuda, cann, inf_ngraph and vkcom
* fix cuda backend
* test commit for cuda
* test cuda backend
* remove debug message from cuda backend
* use cpu dispatcher
* fix neon macro undef in dispatcher
* fix dispatcher
* fix inner kernel for neon aarch64
* fix compiling issue on armv7; try fixing accuracy issue on other platforms
* broadcast C with beta multiplied; improve func namings
* fix bug for avx and avx2
* put all platform-specific kernels in dispatcher
* fix typos
* attempt to fix compile issues on x64
* run old gemm when neon, avx, avx2 are all not available; add kernel for armv7 neon
* fix typo
* quick fix: add macros for pack4
* quick fix: use vmlaq_f32 for armv7
* quick fix for missing macro of fast gemm pack f32 4
* disable conformance tests when optimized branches are not supported
* disable perf tests when optimized branches are not supported
* decouple cv_try_neon and cv_neon_aarch64
* drop googlenet_2023; add fastGemmBatched
* fix step in fastGemmBatched
* cpu: fix initialization ofb; gpu: support batch
* quick followup fix for cuda
* add default kernels
* quick followup fix to avoid macro redef
* optmized kernels for lasx
* resolve mis-alignment; remove comments
* tune performance for x64 platform
* tune performance for neon aarch64
* tune for armv7
* comment time consuming tests
* quick follow-up fix
OCL_FP16 MatMul with large batch
* Workaround FP16 MatMul with large batch
* Fix OCL reinitialization
* Higher thresholds for INT8 quantization
* Try fix gemm_buffer_NT for half (columns)
* Fix GEMM by rows
* Add batch dimension to InnerProduct layer test
* Fix Test_ONNX_conformance.Layer_Test/test_basic_conv_with_padding
* Batch 16
* Replace all vload4
* Version suffix for MobileNetSSD_deploy Caffe model
Resolve uncovered CUDA dnn layer #24080
### Pull Request Readiness Checklist
* Gelu activation layer on CUDA
* Try to relax GEMM from ONNX
resolves https://github.com/opencv/opencv/issues/24064
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake
DNN: optimize the speed of general Depth-wise #23952
Try to solve the issue: https://github.com/opencv/opencv/issues/23941
### Pull Request Readiness Checklist
See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request
- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [ ] There is a reference to the original bug report and related work
- [ ] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
Patch to opencv_extra has the same branch name.
- [ ] The feature is well documented and sample code can be built with the project CMake
dnn: add layer normalization for vision transformers
* add layer norm onnx parser, impl and tests
* add onnx graph simplifier for layer norm expanded
* handle the case when constants are of type Initializer
* add test case for layer norm expanded with initializers
* use CV_Assert & CV_CheckType in place of CV_Assert_N; use forward_fallback for OCL_FP16
* use const ref / ref in parameters of invoker::run; extract inner const if from nested loop; use size_t in place of ull
* template hasBias
* remove trailing whitespace
* use pointer parameter with null check; move normSize division & mean_square division outside of loop; use std::max to ensure positive value before std::sqrt
* refactor implementation, optimize parallel_for
* disable layer norm expanded
* remove the removal of layer norm optional outputs
DNN: reduce the memory used in convolution layer
* reduce the memory in winograd and disabel the test when usage memory is larger than 2gb.
* remove VERY_LOG tag
